{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_v5cfzxr4wckg","handle":"visionstory-mcp","url":"https://wellknown.network/agents/visionstory-mcp","links":{"self":"https://wellknown.network/agents/visionstory-mcp/record.json","html":"https://wellknown.network/agents/visionstory-mcp","markdown":"https://wellknown.network/agents/visionstory-mcp/record.md","api":"https://wellknown.network/api/v1/agents/visionstory-mcp","status":"https://wellknown.network/api/v1/agents/visionstory-mcp/status","claim":"https://wellknown.network/agents/visionstory-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/visionstory-mcp/claim.json","badge":"https://wellknown.network/agents/visionstory-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:visionstory-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"visionstory-mcp","summary":"MCP server for the VisionStory API - task-oriented tools for AI talking-avatar video generation.","description":"# visionstory-mcp\n\nMCP server for the [VisionStory API](https://developers.visionstory.ai) — task-oriented tools that let AI agents (Claude Desktop, Cursor, and any Model Context Protocol client) generate AI talking-avatar videos without writing code.\n\nIt exposes all **27 public API operations**, kept in sync with the [`visionstory`](https://pypi.org/project/visionstory/) SDK and `visionstory` CLI:\n\n- Talking-avatar videos: generate, get, list, and delete.\n- Avatars and voices: create or clone, list, and delete.\n- AI Video: discover models, estimate cost, generate, get one or many, list, and delete.\n- Images, speech, and audio: discover image models, generate or edit images, synthesize localized MP3 audio, transcribe speech, and align known text with word timestamps.\n- Assets and account: upload, list, and delete assets; list avatar models; check credits.\n\nOn startup, the local server checks the shared release manifest and writes an upgrade notice to stderr when a newer package is available. Agents can read `visionstory://release` for the installed and latest versions, feature highlights, release notes, and the upgrade command. Set `VISIONSTORY_UPDATE_CHECK=0` to disable the check.\n\nDelete tools require `confirm=true` after explicit user confirmation. The local stdio server keeps direct local-file support for avatar, voice, talking-video, and asset workflows.\n\n## Install & run\n\nRequires an API key — create one on the [VisionStory API keys page](https://developers.visionstory.ai/api-keys) (Pro plan and up) and set it as `VISIONSTORY_API_KEY`.\n\nAdd it to Claude Desktop (or any MCP client):\n\n```json\n{\n  \"mcpServers\": {\n    \"visionstory\": {\n      \"command\": \"uvx\",\n      \"args\": [\"visionstory-mcp\"],\n      \"env\": { \"VISIONSTORY_API_KEY\": \"sk-vs-xxxxxxxxxxxxxxxxxxx\" }\n    }\n  }\n}\n```\n\n`generate_video` and `generate_ai_video` submit and poll to completion, returning the final video URL — one call in, one result out. `create_speech` returns standard MCP audio content plus u…","publisher":null,"homepage":"https://developers.visionstory.ai/guides/for-agents","repository":null,"version":"0.0.9","license":null,"protocols":["mcp"],"tags":["agent","ai","avatar","mcp","model-context-protocol","talking-avatar","video-generation","visionstory"],"pricing":null,"endpoints":[{"url":"pypi:visionstory-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"media.video-generation","name":"Video Generation","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.768,"provenance":"derived"}],"categories":["dev","media"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"visionstory-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:14.078Z","publishedAt":"2026-09-04T17:35:27.585356Z","latestVersion":"0.0.9"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"visionstory-mcp","url":"https://pypi.org/project/visionstory-mcp/","firstSeenAt":"2026-09-10T15:23:42.898Z","fetchedAt":"2026-09-10T15:23:42.898Z","normalizedAt":"2026-09-10T15:23:42.898Z"}]},"firstSeenAt":"2026-09-10T15:23:42.898Z","updatedAt":"2026-09-10T15:25:14.078Z"}